Alavi Arash, Bogu Gireesh K, Wang Meng, Rangan Ekanath Srihari, Brooks Andrew W, Wang Qiwen, Higgs Emily, Celli Alessandra, Mishra Tejaswini, Metwally Ahmed A, Cha Kexin, Knowles Peter, Alavi Amir A, Bhasin Rajat, Panchamukhi Shrinivas, Celis Diego, Aditya Tagore, Honkala Alexander, Rolnik Benjamin, Hunting Erika, Dagan-Rosenfeld Orit, Chauhan Arshdeep, Li Jessi W, Li Xiao, Bahmani Amir, Snyder Michael P
Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA.
Department of Computer Science, Stanford University, Stanford, CA, USA.
medRxiv. 2021 Jun 21:2021.06.13.21258795. doi: 10.1101/2021.06.13.21258795.
Early detection of infectious disease is crucial for reducing transmission and facilitating early intervention. We built a real-time smartwatch-based alerting system for the detection of aberrant physiological and activity signals (e.g. resting heart rate, steps) associated with early infection onset at the individual level. Upon applying this system to a cohort of 3,246 participants, we found that alerts were generated for pre-symptomatic and asymptomatic COVID-19 infections in 78% of cases, and pre-symptomatic signals were observed a median of three days prior to symptom onset. Furthermore, by examining over 100,000 survey annotations, we found that other respiratory infections as well as events not associated with COVID-19 (e.g. stress, alcohol consumption, travel) could trigger alerts, albeit at a lower mean period (1.9 days) than those observed in the COVID-19 cases (4.3 days). Thus this system has potential both for advanced warning of COVID-19 as well as a general system for measuring health via detection of physiological shifts from personal baselines. The system is open-source and scalable to millions of users, offering a personal health monitoring system that can operate in real time on a global scale.
传染病的早期检测对于减少传播和促进早期干预至关重要。我们构建了一个基于智能手表的实时警报系统，用于检测个体层面与早期感染发作相关的异常生理和活动信号（如静息心率、步数）。将该系统应用于3246名参与者的队列中时，我们发现78%的病例针对症状前和无症状的COVID-19感染生成了警报，症状前信号在症状发作前的中位时间为三天。此外，通过检查超过10万条调查注释，我们发现其他呼吸道感染以及与COVID-19无关的事件（如压力、饮酒、旅行）也可能触发警报，尽管其平均时间（1.9天）比COVID-19病例中观察到的时间（4.3天）短。因此，该系统既具有COVID-19提前预警的潜力，也具有通过检测个人基线生理变化来衡量健康状况的通用系统的潜力。该系统是开源的，可扩展至数百万用户，提供了一个能够在全球范围内实时运行的个人健康监测系统。
